© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35099
    Prev
    Next
    INDEX
    Explanations

    prendre

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ਾ
    0.58
    trend
    0.57
     पुरंदरे
    0.54
    া
    0.53
     unapolog
    0.52
     attractions
    0.52
     takeaways
    0.52
    trends
    0.52
    ۀ
    0.52
     trending
    0.52
    POSITIVE LOGITS
     hoved
    0.53
    t
    0.52
    m
    0.52
    leich
    0.51
     rø
    0.51
    轂
    0.51
     vit
    0.50
    n
    0.49
     Arch
    0.48
    ஸ்ப
    0.48
    Activations Density 0.001%

    No Known Activations